vLLM plugin for the NVFP4-CB / FP8-CB product-codebook weight formats: 2-6 bit-per-weight LLM quantization served by dedicated CUDA decode and prefill kernels.
I love discovering Mac apps that use AI, so I built MacAIApps to collect them in one place.You can browse by category and find apps you might otherwise miss. Comments URL: https://news.ycombinator.com/item?id=49404725 Points: 1 # Comments: 0
Always-on containerized dev environment for AI coding agents, driven over SSH+tmux.
The harness-transcript extraction lib (DEC e8b2f397 increment ii; the d774d311 build item): parse agent-harness session transcripts (Claude Code JSONL first) into their append-only record DAG, walk the active path, extract user-facing prose both sides, and de…
The harness-transcript extraction lib (DEC e8b2f397 increment ii; the d774d311 build item): parse agent-harness session transcripts (Claude Code JSONL first) into their append-only record DAG, walk the active path, extract user-facing prose both sides, and de…
